You can deploy this model and start earning money today!

residuals/
qwen2.5-7b

Name: qwen2.5-7b
Availability: InStock

Views

No views yet

Instruction Residuals

This repository contains instruction residuals (delta weights) computed as the parameter-wise difference between Qwen/Qwen2.5-7B-Instruct and Qwen/Qwen2.5-7B.

Apply these residuals to the base model to reconstruct the instruction-tuned weights without retraining.

Usage

python

from transformers import AutoModelForCausalLM, AutoTokenizer
from residuals import Residuals

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B")
tok = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-7B")

res = Residuals.from_pretrained("residuals/qwen2.5-7b")
res.apply(base, base_tokenizer=tok)

Provenance

Created at: 2025-10-25T16:09:23.454524+00:00
DType: float32
Parameters: 339
Shapes hash: cf9d6257268ea1e66311ede6da3b26edcb8a440a6952f4a8271b41db6abc493d
Names hash: 4d2eff4cabea80e69a6d439aa4d36bc50e1d699d0c8eec4da89ae58c02d99e5c
Base model: Qwen/Qwen2.5-7B
Instruction model: Qwen/Qwen2.5-7B-Instruct

Files

model.safetensors: Serialized residual tensors (safetensors format).
(optional) model.safetensors.index.json + shard files model-00001-of-000N.safetensors, ... for multi-part weights.
config.json: Residuals metadata and provenance.
tokenizer files: Saved tokenizer for compatibility.

About this format

These are additive residuals (task vectors). Applying them to the base model's parameters reconstructs the instruction-tuned model.

Tools

Generated with the residuals Python package. Install via: pip install residuals.

PyPI: https://pypi.org/project/residuals/
Source: https://github.com/omarish/residuals